ApX logoApX logo

GLM-4

Parameters

32B

Context Length

128K

Modality

Text

Architecture

Dense

License

Custom Commercial License with Restrictions

Release Date

15 Jan 2024

Knowledge Cutoff

Dec 2023

System Requirements

VRAM requirements for different quantization methods and context sizes

1,024 tokens

68.77 GB VRAM

Consumer

4x RTX 4090

24GB VRAM

Datacenter

1x NVIDIA A100

80GB VRAM

Apple Silicon

1x Apple M3 Max

128GB VRAM

128,000 tokens

77.10 GB VRAM

Consumer

4x RTX 4090

24GB VRAM

Datacenter

1x NVIDIA A100

80GB VRAM

Apple Silicon

1x Apple M3 Max

128GB VRAM

Architecture Diagram

Input TokensToken EmbeddingPosition: AbsoluteHidden: 6.1k · Context: 128K · Vocab: 151.6kx 61 layersRMSNormPre-AttentionMulti-Head Attention48Q / 2KV headsHead dim: 128+RMSNormPre-FFNFeed-Forward NetworkSwiGLUIntermediate: 13.7k+Final RMSNormOutput Logits

Evaluation Benchmarks

No evaluation benchmarks for GLM-4 available.

Rankings

Overall Rank

-

Coding Rank

-

About GLM-4

The GLM-4 32B model is a foundational large language model developed by Z.ai, representing a significant scaling of the General Language Model (GLM) architecture to 32 billion parameters. This model is engineered to balance high-order reasoning capabilities with computational efficiency, serving as a versatile core for advanced agentic applications, complex code generation, and intricate bilingual text processing. It occupies a strategic position within the GLM-4 family, providing the structural complexity necessary for sophisticated linguistic understanding while maintaining a footprint suitable for diverse deployment environments.

Technically, the model utilizes a dense transformer architecture optimized through extensive pre-training on a massive corpus of 15 trillion tokens. This training set includes a substantial proportion of synthetic reasoning data, specifically curated to enhance the model's logical inference and problem-solving skills. The architectural design integrates modern advancements such as Rotary Positional Embeddings (RoPE) and Group Query Attention (GQA), which together facilitate stable performance and efficient inference over a context window of up to 128,000 tokens. To ensure high-quality output, the model undergoes a multi-stage post-training pipeline involving human preference alignment, rejection sampling, and reinforcement learning.

GLM-4 32B is specifically optimized for scenarios requiring structured outputs and autonomous tool interaction. Its performance characteristics make it particularly effective for engineering-grade code generation, precise search-based question answering, and the creation of detailed technical artifacts. The model's refined instruction-following and robust function-calling capabilities enable it to act as the primary engine for intelligent agents that need to plan and execute multi-step tasks across diverse software environments and knowledge domains.

Technical Specifications

Attention

Attention Structure

Multi-Head Attention

Attention Heads

48

Key-Value Heads

2

Attention Head Dimension

128

Position Embedding

Absolute Position Embedding

RoPE Theta

-

Sliding Window Attention

No

Sliding Window Size

-

Sliding Window Ratio

-

Linear Attention

-

Linear Attention Ratio

-

Normalization

RMS Normalization

Activation Function

SwigLU

Dimensions

Hidden Dimension Size

6,144

Number of Layers

61

FFN Intermediate Size (Dense)

13,696

Multi-Token Prediction Heads

-

Tokenizer

Vocabulary Size

151,552

About GLM Family

General Language Models from Z.ai


Other GLM Family Models